proxy: Settings dataclass + cache-ratio gate + P-pick offload penalty (B4, M2, M3, D5)

- Replace mutable module constants (HEAVY_THRESHOLD/OVERLOAD_FACTOR/
  MAX_OFFLOAD_INFLIGHT/PREFILL_THROUGHPUT/RDMA_OVERHEAD_S/
  CACHE_CAPACITY_BLOCKS) with a Settings dataclass + SETTINGS singleton.
  __main__ now mutates SETTINGS so CLI overrides survive even when the
  module is imported as a library (e.g. by tests/) (D5).
- Add --max-offload-inflight CLI flag (M3) and read it from SETTINGS.
- Add --cache-gate-ratio CLI flag and a real gate before the cost-model
  branch: if cache_hit/input_length < ratio, mark cache_gate_REASON and
  fall back to colocated. cache_ratio is no longer a write-only field
  (B4).
- P candidate selection penalises instances already running offloaded
  HEAVY prefills, so back-to-back HEAVY requests don't pile onto the
  same P (M2).
- bench.sh forwards --max-offload-inflight / --cache-gate-ratio to the
  proxy.
- Tests cover SETTINGS knobs + the heavy_threshold-driven P-offload
  penalty.

scripts/bench.sh

@@ -35,6 +35,8 @@ HEAVY_THRESHOLD=20000
 NO_OFFLOAD=false
 OVERLOAD_FACTOR_ARG=""
 MAX_BATCHED_TOKENS=""
+MAX_OFFLOAD_INFLIGHT=""
+CACHE_GATE_RATIO=""
 
 # Parse args
 while [[ $# -gt 0 ]]; do
@@ -49,6 +51,8 @@ while [[ $# -gt 0 ]]; do
         --no-offload) NO_OFFLOAD=true; shift ;;
         --overload-factor) OVERLOAD_FACTOR_ARG="$2"; shift 2 ;;
         --max-batched-tokens) MAX_BATCHED_TOKENS="$2"; shift 2 ;;
+        --max-offload-inflight) MAX_OFFLOAD_INFLIGHT="$2"; shift 2 ;;
+        --cache-gate-ratio) CACHE_GATE_RATIO="$2"; shift 2 ;;
         *) echo "Unknown: $1"; exit 1 ;;
     esac
 done
@@ -207,6 +211,12 @@ launch_proxy() {
     if [ -n "$OVERLOAD_FACTOR_ARG" ]; then
         extra_args="$extra_args --overload-factor $OVERLOAD_FACTOR_ARG"
     fi
+    if [ -n "$MAX_OFFLOAD_INFLIGHT" ]; then
+        extra_args="$extra_args --max-offload-inflight $MAX_OFFLOAD_INFLIGHT"
+    fi
+    if [ -n "$CACHE_GATE_RATIO" ]; then
+        extra_args="$extra_args --cache-gate-ratio $CACHE_GATE_RATIO"
+    fi
     if [ "$MODE" = "elastic" ]; then
         local bp_list=""
         for i in $(seq 0 $((N_INSTANCES - 1))); do